1
Detecting Prostate Cancer Using MRI
DataDavid Anderson, Bruce Golden, Ed Wasil,
Howard Zhang
INFORMS Annual Meeting October, 2013
The NCI estimates that 15% of men born today will be diagnosed with prostate cancer
Average costs of $10,000 in the first year after diagnosis
Hard to diagnose
2
Prostate Cancer
Prostate Cancer Diagnosis Methods PSA Test
◦ Non-intrusive◦ High false positive rate
67% sensitivity, 58% specificity (Thompson et al. 2005)
Digital Exam◦ Inconsistent
Biopsy◦ Painful◦ Expensive◦ Possibly severe side effects
3
MRIs to the Rescue?
4
Can we use MRIs to screen for prostate cancer?
◦Will doing so be more cost effective than the current system?
5
Research Question
Data 223 slices of prostates from radical
prostatectomy patients
3 types of MRIs on each slice (Dynamic Contrast Enhanced, Diffusion Weighted, and Magnetic Resonance Spectroscopic Imaging)
119 had cancer (Gleason score of 5 or above)
6
Slices from the same prostate may have similar cancer status and MRI data
Correlation between slices of the same prostate would bias our performance upwards
Correlation in Gleason scores of adjacent slices is 0.30, and for slices two apart it is 0.004
7
Independence of Slices
8
Distribution of Cancer
Three Methods Logistic Regression
Nearest Neighbors Clustering
Augmented Logistic Regression
9
10
Results – Logistic Regression
11
Results – Nearest Neighbors
12
Augmented Logistic Regression Results
Gleason Score
0 – 4 5 – 8
Predicted Healthy
79 22
Predicted Cancer
25 97
13
Augmented Logistic Regression Results
The combined model achieves 82% sensitivity and 76% specificity
Many prostate cancers are slow growing◦ “More men die ‘with’ prostate cancer than ‘from’ it”
Identifying high severity cancer (scores of 7 or 8) is important
14
High Severity Cancer
15
High Severity Results
Gleason Score
0 – 6 7 – 8
Predicted Healthy
151 5
Predicted Cancer
36 31
16
High Severity Results
For high severity cancers, the combined model achieves 81% sensitivity and 86% specificity
Prices for medical services vary widely◦ Biopsies average ~$2100◦ MRIs average ~$700
If MRIs can reduce the number of biopsies by at least 1/3 they will reduce costs
17
Cost Effectiveness
Conclusions MRIs can be used to identify prostate cancer
By looking at each slice of a prostate we can identify where to biopsy
MRIs offer possibly better predictive power than PSA tests, and are less invasive than biopsies
18
Combine MRI types
Automated prediction
Distinguish between high and medium severity cancers
19
Contribution
Collect more data◦ Healthy patients and cancerous
Build models for whole prostates, not slices
Predict specific Gleason scores
20
Future Work
Top Related